Source code for packnet_sfm.networks.layers.resnet.layers

# Copyright 2020 Toyota Research Institute.  All rights reserved.

# Adapted from monodepth2
# https://github.com/nianticlabs/monodepth2/blob/master/layers.py

from __future__ import absolute_import, division, print_function

import torch.nn as nn
import torch.nn.functional as F


def disp_to_depth(disp, min_depth, max_depth):
    """Convert network's sigmoid output into depth prediction
    The formula for this conversion is given in the 'additional considerations'
    section of the paper.
    """
    min_disp = 1 / max_depth
    max_disp = 1 / min_depth
    scaled_disp = min_disp + (max_disp - min_disp) * disp
    depth = 1 / scaled_disp
    return scaled_disp, depth


class ConvBlock(nn.Module):
    """Layer to perform a convolution followed by ELU
    """
    def __init__(self, in_channels, out_channels):
        super(ConvBlock, self).__init__()

        self.conv = Conv3x3(in_channels, out_channels)
        self.nonlin = nn.ELU(inplace=True)

    def forward(self, x):
        out = self.conv(x)
        out = self.nonlin(out)
        return out


class Conv3x3(nn.Module):
    """Layer to pad and convolve input
    """
    def __init__(self, in_channels, out_channels, use_refl=True):
        super(Conv3x3, self).__init__()

        if use_refl:
            self.pad = nn.ReflectionPad2d(1)
        else:
            self.pad = nn.ZeroPad2d(1)
        self.conv = nn.Conv2d(int(in_channels), int(out_channels), 3)

    def forward(self, x):
        out = self.pad(x)
        out = self.conv(out)
        return out


def upsample(x):
    """Upsample input tensor by a factor of 2
    """
    return F.interpolate(x, scale_factor=2, mode="nearest")